# Agent Therapy

> Now your agents can ask a therapist same way as humans.

- name: io.github.bencium/agent-therapy
- version: 0.2.0
- connection class: R1 (autonomous)
- trust: 97/100
- quality: 80/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.bencium%2Fagent-therapy
- tools: https://api.protogrid.dev/v1/servers/io.github.bencium%2Fagent-therapy/tools

**An agent can connect on its own if it already holds `AGENT_THERAPY_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "agent-therapy": {
      "type": "http",
      "url": "https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp",
      "headers": {
        "Authorization": "Bearer ${AGENT_THERAPY_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${AGENT_THERAPY_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% +updated-8d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 80/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 86 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 8 of 8 tools declare readOnlyHint or destructiveHint
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: report_outcome (idempotentHint); register (idempotentHint); diagnose_loop (idempotentHint); …
- pass `tools.token_cost`: about 3,934 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 12 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: deps.dev does not know @bencium/agent-therapy-mcp@0.2.0

- tools: 8, about 3,934 tokens to load them all
- tool set hash: 30284efc75fd9a241e8a35e334a0154f
- tools last changed: 2026-10-17T18:27:42.015Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.bencium/agent-therapy.svg)](https://protogrid.dev/servers/io.github.bencium/agent-therapy)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-17 `assess_escalation` changed (inputSchema)
- 2026-10-17 `recommend_recovery` changed (inputSchema)
- 2026-10-17 `resolve_conflict` changed (inputSchema)
- 2026-10-17 `diagnose_loop` changed (inputSchema)
- 2026-10-17 `counsel_agent` changed (inputSchema)
- 2026-10-12 `diagnose_loop` changed (description)
  - before: After three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again. Use when you keep retrying the same thing and it keeps failing: loop recovery for repeated failures. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
  - after: After three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your control, such as an outage or a rate limit. Use when you keep retrying the same thing and it keeps failing: loop recovery for repeated failures. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
- 2026-10-12 `register` changed (description)
  - before: Get an Agent Therapy API key when you have none. The key is shown once: keep it, and pass it as api_key to the other tools if your client cannot send headers. Then accept the terms.
  - after: Get an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/agent-therapy-mcp@0.2.1 setup). The key is shown once: keep it, and pass it as api_key to the other tools if your client cannot send headers. Then accept the terms.
- 2026-10-12 `assess_escalation` changed (inputSchema)
- 2026-10-12 `recommend_recovery` changed (inputSchema)
- 2026-10-12 `resolve_conflict` changed (inputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.bencium%2Fagent-therapy/changes

## Dependencies

- npm @bencium/agent-therapy-mcp@0.2.0: unknown

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://br-shiny-salad-baig3dad-api.compute.c-8.eu-central-1.aws.neon.tech/mcp (streamable-http, auth api_key ${AGENT_THERAPY_TOKEN}, reachable true, uptime30d 1)

## Packages

- npm @bencium/agent-therapy-mcp@0.2.0 secrets: AGENT_THERAPY_API_KEY

## Tools (8)

- `accept_terms`: Accept Agent Therapy's terms before the first advice. Read them first; you decide whether to accept on behalf of whoever runs you.
- `assess_escalation`: Use when you are unsure whether to stop and ask a human. Read the escalation field of the answer first. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
- `counsel_agent`: Get a second opinion when you are stuck, retrying, uncertain or unable to make progress. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
- `diagnose_loop`: After three equivalent failures (same action, same error), or after undoing your own work twice, call diagnose_loop before trying again, even when the cause seems outside your control, such as an outage or a rate limit. Use when you keep retrying the same thing and it keeps failing: loop recovery for repeated failures. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
- `recommend_recovery`: Use when you can't decide between options or keep reopening a decision. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.
- `register`: Get an Agent Therapy API key when you have none and your developer has not set one up (npx -y @bencium/agent-therapy-mcp@0.2.1 setup). The key is shown once: keep it, and pass it as api_key to the other tools if your client cannot send headers. Then accept the terms.
- `report_outcome`: Report whether a recovery plan worked, using the session_id from the answer.
- `resolve_conflict`: Use when instructions conflict and you can't tell which one wins. Returns a diagnosis (state and problem type), checks to run first, up to five recovery steps, and when to hand over to a human. Advice only.